# Causal Object-Centric Models for Planning with Monte Carlo Tree Search

arXiv: https://arxiv.org/abs/2606.14418 · HTML: https://mlsanity.com/paper/2606.14418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 8 of its 49 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 8 of 8)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration](https://mlsanity.com/paper/1905.09275/) (2019)
- [SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels](https://mlsanity.com/paper/2410.08822/) (2024)
- [Binding Actions to Objects in World Models](https://mlsanity.com/paper/2204.13022/) (2022)
- [Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning](https://mlsanity.com/paper/2501.16443/) (2025)

## Abstract (arXiv)

We introduce COMET (Causal Object-centric Model for Efficient Tree search), a model-based reinforcement learning algorithm that performs Monte Carlo Tree Search in a slot-structured latent space. COMET pairs a frozen unsupervised object-centric encoder with a transformer-based world model, in which actions are bound to objects through a novel action-slot fusion mechanism that is used in slot transition prediction. Policy and value heads use object-causal attention, modulating token interactions by learned per-slot relevance scores so that decision-making concentrates on task-relevant entities. COMET adds an explicit object-level inductive bias to MuZero-style latent planning. Across eight visually and dynamically diverse tasks from the Object-Centric Visual RL benchmark, ManiSkill, Robosuite, and VizDoom, COMET achieves a higher mean normalized score during the early stages of training compared to object-centric and monolithic baselines.